This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: EE 278 Wednesday, November 11, 2009 Statistical Signal Processing Handout #16 Midterm Examination Solutions 1. Inequalities. a. e S is a convex function so by Jensens inequality E( e S ) e E( s ) = e Since E( S ) = 1. b. S is a concave function so by Jensens inequality E( S ) E( S ) 1 2 = 1 Since E( S ) = 1. 2. Exponentials. a. To find E( S  S > 5), we need to find the pdf of S given the event S > 5. Let event A = { S > 5 } . f S  A ( s ) = f S ( s ) P ( S A ) if s A , and 0 , otherwise = e s P ( S > 5) = e s integraltext 5 e s ds = e s e 5 = e ( s 5) if s > 5, and 0 , otherwise Let s prime = s 5 so s = s prime + 5. E( S  A ) = integraldisplay 5 sf S  A ( s ) ds = integraldisplay 5 se ( s 5) ds = integraldisplay ( s prime + 5) e s prime ds prime = integraldisplay s prime e s prime ds prime + integraldisplay 5 e s prime ds prime = 1 + 5 = 6 b. To find E( S  S + T ), we first should recognize that E( S + T  S + T ) = E( S  S + T ) + E( T  S + T ) S + T = 2 E( S  S + T ) Page 2 of 4 EE 278, Fall 2009 The first line follows from linearity of expectation. The second line follows because S and T are independent and have the same distribution so E( S  S + T ) = E( T  S + T )....
View
Full
Document
This note was uploaded on 11/28/2009 for the course EE 278 taught by Professor Balajiprabhakar during the Fall '09 term at Stanford.
 Fall '09
 BalajiPrabhakar
 Signal Processing

Click to edit the document details